37 citations · 73 across the 6 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
eess.AS2021
A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation
Martin Strauss, Jouni Paulus, Matteo Torcoli +1
This paper describes a hands-on comparison on using state-of-the-art music source separation deep neural networks (DNNs) before and after task-specific fine-tuning for separating s…
eess.AS2021★ 29 cited
A Flow-Based Neural Network for Time Domain Speech Enhancement
Martin Strauss, Bernd Edler
Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adve…